Reinforcement Learning with Guarantees that Hold for Ever.
Ernst Moritz HahnMateo PerezSven ScheweFabio SomenziAshutosh TrivediDominik WojtczakPublished in: FMICS (2022)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- state space
- optimal policy
- reinforcement learning algorithms
- temporal difference
- markov decision processes
- real time
- robotic control
- learning problems
- model free
- action space
- control problems
- direct policy search
- initial state
- optimal control
- monte carlo
- supervised learning
- hidden markov models
- learning process
- information systems
- neural network